Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 30243
    Prev
    Next
    INDEX
    Explanations

    movie

    np_max-act · gemini-2.0-flash

    This neuron fires on tokens naming leisure‐and‐entertainment activities, especially reading (book) and watching (movie/TV/show).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     field
    -0.08
     toDate
    -0.06
     volunteers
    -0.06
     FIELD
    -0.06
    Guide
    -0.06
     tables
    -0.06
     kissed
    -0.06
    .ie
    -0.06
     hatred
    -0.06
     گرف
    -0.06
    POSITIVE LOGITS
    hower
    0.07
    flix
    0.07
    <Animator
    0.06
    当然
    0.06
     Allows
    0.06
    中
    0.06
     Malaysian
    0.06
    culos
    0.06
     след
    0.06
    claration
    0.06
    Activations Density 0.022%

    No Known Activations